English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recently, an event-based end-to-end model (SEDT) has been proposed for soundevent detection (SED) and achieves competitive performance. However, comparedwith the frame-based model, it requires more training data with temporalannotations to improve the localization ability. Synthetic data is analternative, but it suffers from a great domain gap with real recordings.Inspired by the great success of UP-DETR in object detection, we propose toself-supervisedly pre-train SEDT (SP-SEDT) by detecting random patches (onlycropped along the time axis). Experiments on the DCASE2019 task4 dataset showthe proposed SP-SEDT can outperform fine-tuned frame-based model. The ablationstudy is also conducted to investigate the impact of different loss functionsand patch size.

SP-SEDT: Self-supervised Pre-training for Sound Event Detection Transformer